A knowledge discovery and visualisation method for unearthing emotional states from physiological data
- PDF / 1,532,029 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 65 Downloads / 126 Views
ORIGINAL ARTICLE
A knowledge discovery and visualisation method for unearthing emotional states from physiological data Nectarios Costadopoulos1 · Md Zahidul Islam1 · David Tien1 Received: 3 October 2019 / Accepted: 18 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In this paper we propose a knowledge discovery and visualisation method for unearthing emotional states from physiological data typically available from wearable devices. In addition we investigate the viability of using a limited set of wearable sensors to extract decision tree rules which are representative of physiological changes taking place during emotional changes. Our method utilised a fusion of pre-processing and classification techniques using decision trees to discover logic rules relating to the valence and arousal emotional dimensions. This approach normalised the signal data in a manner that enabled accurate classification and generated logic rules for knowledge discovery. Furthermore, the use of three target classes for the emotional dimensions was effective at denoising the data and further enhancing classification and useful rule extraction. There are three key contributions in this work, firstly an exploration and validation of our knowledge discovery methodology, secondly successful extraction of high accuracy rules derived from physiological data and thirdly knowledge discovery and visualisation of relationships within-participant physiological data that can be inferred relating to emotions. Additionally, this work may be utilised in areas such as the medical sciences where interpretable rules are required for knowledge discovery. Keywords Knowledge discovery · Knowledge visualisation · Decision trees · Physiological data · Logic rules · Interpretable machine learning · Wearables · Sensors · Affective computing · Plethysmography · Galvanic skin response
1 Introduction The widespread use of wearable devices [10] made by Apple, Huawei, Samsung and Garmin for fitness and health applications made us curious about further uses beyond sport, health and sleep tracking. According to the International Data Corporation [27] there were 73 million units shipped by the start of 2020, with the market growing by 30% annualy. The growth in the uptake of these devices has generated a research opportunity. To date, there has been limited research on using wearable sensors such as plethysmography, respiration, galvanic skin response, and
* Nectarios Costadopoulos [email protected] Md Zahidul Islam [email protected] David Tien [email protected] 1
School of Computing and Mathematics, Charles Sturt University, Bathurst, Australia
temperature, to extract information on the underlying emotional state of an individual. A common complaint in the affective computing field as summed up by Smets et al. [50] is that there was (a) a lack of labelled datasets which have been collected under rigorous experimental conditions and (b) that the few datasets that exist suffered from a lack of dimensionality (~ 10–30
Data Loading...
